icloud-ecnu / OparaLinks
Opara is a lightweight and resource-aware DNN Operator parallel scheduling framework to accelerate the execution of DNN inference on GPUs.
☆21Updated 7 months ago
Alternatives and similar repositories for Opara
Users that are interested in Opara are comparing it to the libraries listed below
Sorting:
- iSpot is a lightweight and cost-effective instance provisioning framework for Directed Acyclic Graph (DAG)-style big data analytics, in …☆11Updated last year
- spotDNN is a heterogeneity-aware spot instance provisioning framework to provide predictable performance for DDNN training workloads in t…☆15Updated last year
- iGniter, an interference-aware GPU resource provisioning framework for achieving predictable performance of DNN inference in the cloud.☆38Updated last year
- DelayStage is a simple yet effective stage delay scheduling strategy to interleave the cluster resources across the parallel stages, so a…☆14Updated last year
- ebrowser, an energy-efficient and lightweight human interaction framework without degrading the user experience in mobile Web browsers.☆12Updated last year
- Prophet is a predictable communication scheduling strategy to schedule the gradient transfer in an adequate order, with the aim of maximi…☆16Updated last year
- ☆8Updated 3 years ago
- Reading paper list for iCloud group☆14Updated last month
- ☆12Updated last year
- ☆42Updated last year
- This repository is established to store personal notes and annotated papers during daily research.☆140Updated this week
- A direct convolution library targeting ARM multi-core CPUs.☆12Updated 8 months ago
- ☆37Updated last month
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆60Updated last year
- ☆13Updated 5 months ago
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆120Updated last week
- An interference-aware scheduler for fine-grained GPU sharing☆143Updated 6 months ago
- ☆129Updated 8 months ago
- λDNN is a cost-efficient function resource provisioning framework to minimize the monetary cost and guarantee the performance for DDNN tr…☆23Updated last year
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆98Updated 2 years ago
- ☆32Updated 2 years ago
- Summary of some awesome work for optimizing LLM inference☆95Updated 2 months ago
- Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.☆89Updated 2 years ago
- ☆80Updated 2 years ago
- High performance Transformer implementation in C++.☆129Updated 6 months ago
- A lightweight design for computation-communication overlap.☆155Updated last month
- ☆31Updated last year
- ☆150Updated last year
- ☆18Updated last year
- Official implementation for the paper Lancet: Accelerating Mixture-of-Experts Training via Whole Graph Computation-Communication Overlapp…☆13Updated 10 months ago